Re: [PATCH mm-new v9] mm: vmscan: retry folios written back while isolated for traditional LRU

[Barry Song <baohua@kernel.org>]

On Fri, Sep 18, 2026 at 10:12 AM Ridong Chen <ridong.chen@linux.dev> wrote:
[...]
> >
> > I wouldn't necessarily call it a fix, as keeping the swap cache for
> > those folios can sometimes help with future hits. For example, we may
> > hit those folios again before they are reclaimed. So it's a
> > double-edged sword.
> >
> > That said, the cold/hot inversion is a real problem that we should
> > fix. Ideally, we should find a way to restore the missed
> > `folio_rotate_reclaimable()` behavior, conceptually something like:
> >
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index fde28d0a647d..5ee296474b48 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -891,7 +891,10 @@ long remove_mapping(struct address_space
> > *mapping, struct folio *folio)
> >    */
> >   void folio_putback_lru(struct folio *folio)
> >   {
> > -       folio_add_lru(folio);
> > +       if (folio_has_been_writtenback_due_reclaim(folio))
> > +               folio_add_lru_tail(folio);
> > +       else
> > +               folio_add_lru(folio);
> >          folio_put(folio);               /* drop ref from isolate */
> >   }
> >
>
> That is a good idea. But I am not sure I can find the correct way to do it. I
> will give it a try and get back to you.
>

Maybe something like the below?  I haven't tested it.

diff --git a/mm/vmscan.c b/mm/vmscan.c
index fde28d0a647d..906db7d8c043 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1942,7 +1942,7 @@ static bool too_many_isolated(struct pglist_data *pgdat, int file,
  *
  * Note: The caller must not hold any lruvec lock.
  */
-static unsigned int move_folios_to_lru(struct list_head *list)
+static unsigned int move_folios_to_lru(struct list_head *list, bool do_rotate)
 {
 	int nr_pages, nr_moved = 0;
 	struct lruvec *lruvec = NULL;
@@ -1989,7 +1989,16 @@ static unsigned int move_folios_to_lru(struct list_head *list)
 			continue;
 		}
 
-		lruvec_add_folio(lruvec, folio);
+		/*
+		 * Put folios that may have missed folio_rotate_reclaimable() at the tail
+		 * to avoid cold/hot inversion
+		 */
+		if (do_rotate && !folio_test_active(folio) && !folio_mapped(folio) &&
+		    !folio_test_dirty(folio) && !folio_test_writeback(folio))
+			lruvec_add_folio_tail(lruvec, folio);
+		else
+			lruvec_add_folio(lruvec, folio);
+
 		nr_pages = folio_nr_pages(folio);
 		nr_moved += nr_pages;
 		if (folio_test_active(folio))
@@ -2106,7 +2115,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 	nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false,
 					 lruvec_memcg(lruvec));
 
-	move_folios_to_lru(&folio_list);
+	move_folios_to_lru(&folio_list, true);
 
 	mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc),
 					stat.nr_demoted);
@@ -2217,8 +2226,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move folios back to the lru list.
 	 */
-	nr_activate = move_folios_to_lru(&l_active);
-	nr_deactivate = move_folios_to_lru(&l_inactive);
+	nr_activate = move_folios_to_lru(&l_active, false);
+	nr_deactivate = move_folios_to_lru(&l_inactive, false);
 
 	count_vm_events(PGDEACTIVATE, nr_deactivate);
 	count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
@@ -5083,7 +5092,7 @@ static int evict_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 			folio_set_active(folio);
 	}
 
-	move_folios_to_lru(&list);
+	move_folios_to_lru(&list, true);
 
 	walk = current->reclaim_state->mm_walk;
 	if (walk && walk->batched) {